{
  "aliases": [],
  "authors": [],
  "details": {
    "availability": "Ungated annotation files and multipart image-archive manifest.",
    "dataset_profile": {
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/TongUI-agent/TongUI-agent/HEAD/docs/train.md",
          "population": "TongUI-collected GUI-Net-1M data, excluding added external mixtures",
          "qualifier": "approximately",
          "unit": "training trajectories",
          "value": 1000000
        }
      ],
      "evidence_urls": [
        "https://huggingface.co/datasets/Bofeee5675/GUI-Net-1M/raw/main/README.md",
        "https://raw.githubusercontent.com/TongUI-agent/TongUI-agent/HEAD/docs/train.md"
      ],
      "formats": [
        "JSON annotations",
        "multipart image archives"
      ],
      "modalities": [
        "text",
        "screenshots"
      ],
      "notes": "The source reports an approximate trajectory total; it does not establish per-platform counts or a complete test-split inventory.",
      "splits": [
        "training collection"
      ],
      "supervision": [
        "GUI trajectory supervision from multimodal tutorials"
      ]
    },
    "license_review": {
      "data": {
        "evidence_urls": [
          "https://huggingface.co/datasets/Bofeee5675/GUI-Net-1M/raw/main/README.md"
        ],
        "reason": "Publisher declaration for this dataset packaging; original web/tutorial materials retain applicable rights."
      }
    },
    "release_revision": "60d1e644fcff7d3b62093baec03fe7efeb0d98a1"
  },
  "environments": [
    "unspecified"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T12:30:54Z",
      "role": "primary",
      "sha256": "f30a18d1a533b8f71f436dae2ee7369f8971422bd76527e069499c5bba911912",
      "supports": [
        "name",
        "kind",
        "summary",
        "topics",
        "scope",
        "notes",
        "relations"
      ],
      "url": "https://raw.githubusercontent.com/TongUI-agent/TongUI-agent/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T12:32:07Z",
      "role": "primary",
      "sha256": "314a77eb0ba43bedffbe6869601e41aea41993eaca59d86ba346652c853802d2",
      "supports": [
        "identity",
        "release_status",
        "details.release_revision",
        "details.dataset_profile.formats"
      ],
      "url": "https://huggingface.co/api/datasets/Bofeee5675/GUI-Net-1M"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T12:36:55Z",
      "role": "primary",
      "sha256": "b51acb70c95d079ccbe1de0a685ad7c8a4b3b5bed11e6162e6f7c2f60d78805e",
      "supports": [
        "summary",
        "details.dataset_profile"
      ],
      "url": "https://raw.githubusercontent.com/TongUI-agent/TongUI-agent/HEAD/docs/train.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T12:32:07Z",
      "role": "primary",
      "sha256": "c2df5c3a6dd576ae53f0dc0f72ecab07d93ed034b04336abd2072a6f0d812c64",
      "supports": [
        "licenses.data",
        "details.dataset_profile.formats",
        "notes"
      ],
      "url": "https://huggingface.co/datasets/Bofeee5675/GUI-Net-1M/raw/main/README.md"
    }
  ],
  "id": "url:8c9aaafb918aaf8b4e92",
  "identifiers": {},
  "kind": "dataset",
  "last_verified_at": "2026-10-17T12:30:54Z",
  "licenses": {
    "code": null,
    "data": {
      "basis": "Publisher declaration for this dataset packaging; original web/tutorial materials retain applicable rights.",
      "declared": "apache-2.0",
      "retrieved_at": "2026-10-17T12:32:07Z",
      "url": "https://huggingface.co/datasets/Bofeee5675/GUI-Net-1M/raw/main/README.md"
    },
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/Bofeee5675/GUI-Net-1M"
    }
  ],
  "name": "GUI-Net-1M",
  "notes": "The ungated manifest lists JSON annotations and multipart image archives. Training documentation describes roughly one million collected training trajectories from Wikihow, Baidu Experience and GUI videos; this is distinct from larger mixtures that add external datasets. Platform-specific distribution and exact row counts were not established from this release metadata. Apache-2.0 is the publisher dataset declaration, without a grant of additional rights to upstream tutorial content. No image archive or example record was downloaded.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/TongUI-agent/TongUI-agent/HEAD/README.md",
      "target_id": "arxiv:2504.12679",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "A TongUI-collected training corpus from multimodal web tutorials, distributed as annotation files and split screenshot archives for GUI trajectory supervision.",
  "topics": [
    "data-generation",
    "grounding",
    "imitation-learning"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/Bofeee5675/GUI-Net-1M"
}